Regularized learning is a fundamental technique in online optimization, machine learning,
and many other fields of computer science. A natural question that arises in this context is …

Owing to their connection with generative adversarial networks (GANs), saddle-point
problems have recently attracted considerable interest in machine learning and beyond. By …

We investigate a class of reinforcement learning dynamics where players adjust their
strategies based on their actions’ cumulative payoffs over time—specifically, by playing mixed …

This paper examines the convergence of no-regret learning in games with continuous action
sets. For concreteness, we focus on learning via “dual averaging”, a widely used class of no…

In this paper, we analyze the trajectories of stochastic gradient descent (SGD) with the aim of
understanding their convergence properties in non-convex problems. We first show that the …

This paper examines the long-run behavior of learning with bandit feedback in non-cooperative
concave games. The bandit framework accounts for extremely low-information …

Understanding the behavior of no-regret dynamics in general 𝑁-player games is a fundamental
question in online learning and game theory. A folk result in the field states that, in finite …

We study a class of evolutionary game dynamics defined by balancing a gain determined
by the game's payoffs against a cost of motion that captures the difficulty with which the …

In view of solving convex optimization problems with noisy gradient input, we analyze the
asymptotic behavior of gradient-like flows under stochastic disturbances. Specifically, we focus …

This paper examines the equilibrium convergence properties of no-regret learning with
exponential weights in potential games. To establish convergence with minimal information …